Caveat verdict
Skill Test
skill-test
88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.
Skill testing framework spawning isolated sub-agents to trial skills before installing; requires explicit user approval before any installation with complete isolation of the main session.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
70
security
80
transparency
70
maintenance
Findings (1)
Pattern match critical
Recursive delete from root or home — destructive command
sandbox.md · code · rm -rf /
Permissions & capabilities
No declared permissions — minimal attack surface.
process_exec Is this flag fair?
Thanks — recorded.